Ko, W.-J.W.-J.KoSHAO-YI CHIEN2020-06-162020-06-16201619457871https://scholars.lib.ntu.edu.tw/handle/123456789/502328Face hallucination technique generates high-resolution face images from low-resolution ones. In this paper, we propose a patch based multitask deep learning method for face hallucination, which is robust to blurring of images. Our method is based on fully connected feedforward neural network, and the weights of the final layers are fine-tuned separately on different clusters of patches. Experimental results show that our system outperforms the prior state-of-the-art methods by a significant margin, while using less testing computation time. © 2016 IEEE.deep learning; Face hallucination; superresolutionFeedforward neural networks; Computation time; Deep learning; Deep neural networks; Face hallucination; High resolution; Low resolution; State-of-the-art methods; Super resolution; Face recognitionconference paper10.1109/ICME.2016.75529752-s2.0-84987665991